Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7728
    Prev
    Next
    INDEX
    Explanations

    technical words that are used in a variety of academic or professional fields

    oai_token-act-pair · gemini-2.0-flash

    excellent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expert
    -1.43
    Expert
    -1.40
     excellent
    -1.39
    expert
    -1.30
     Expert
    -1.30
     experts
    -1.29
    excellent
    -1.26
    Excellent
    -1.23
     excellence
    -1.23
     EXPERT
    -1.20
    POSITIVE LOGITS
     Normdatei
    0.60
    djangoproject
    0.59
     مرئيه
    0.58
     Cens
    0.57
    Rinse
    0.56
    uncher
    0.54
    featureID
    0.53
    omock
    0.53
    nsito
    0.52
     CHtml
    0.51
    Activations Density 11.432%

    No Known Activations